{"id":"https://openalex.org/W2914675463","doi":"https://doi.org/10.1109/hpcc/smartcity/dss.2018.00047","title":"Mitigating I/O Impact of Checkpointing on Large Scale Parallel Systems","display_name":"Mitigating I/O Impact of Checkpointing on Large Scale Parallel Systems","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2914675463","doi":"https://doi.org/10.1109/hpcc/smartcity/dss.2018.00047","mag":"2914675463"},"language":"en","primary_location":{"id":"doi:10.1109/hpcc/smartcity/dss.2018.00047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc/smartcity/dss.2018.00047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100364747","display_name":"Nana Wang","orcid":"https://orcid.org/0000-0002-6368-3545"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Nana Wang","raw_affiliation_strings":["Sino-German Joint Software Institute, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Sino-German Joint Software Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041914141","display_name":"Qingzheng Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingzheng Sun","raw_affiliation_strings":["Sino-German Joint Software Institute, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Sino-German Joint Software Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330538","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0002-4911-1161"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Sino-German Joint Software Institute, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Sino-German Joint Software Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079362609","display_name":"Depei Qian","orcid":"https://orcid.org/0000-0002-5382-1473"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Depei Qian","raw_affiliation_strings":["Sino-German Joint Software Institute, Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Sino-German Joint Software Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100364747"],"corresponding_institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.21279124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8580724596977234},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.582118034362793},{"id":"https://openalex.org/keywords/file-system","display_name":"File system","score":0.5618786215782166},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5609322786331177},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4983048439025879},{"id":"https://openalex.org/keywords/interconnection","display_name":"Interconnection","score":0.4958694875240326},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.43498554825782776},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3121473789215088},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2747540771961212}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8580724596977234},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.582118034362793},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.5618786215782166},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5609322786331177},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4983048439025879},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.4958694875240326},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.43498554825782776},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3121473789215088},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2747540771961212},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcc/smartcity/dss.2018.00047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc/smartcity/dss.2018.00047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W162436151","https://openalex.org/W163470805","https://openalex.org/W1545979834","https://openalex.org/W2003797551","https://openalex.org/W2014413779","https://openalex.org/W2033656974","https://openalex.org/W2074787299","https://openalex.org/W2078837027","https://openalex.org/W2126658609","https://openalex.org/W2133046454","https://openalex.org/W2161416813","https://openalex.org/W2165751385","https://openalex.org/W2165857095","https://openalex.org/W2171938442","https://openalex.org/W2581192167","https://openalex.org/W3143778233","https://openalex.org/W4237019239","https://openalex.org/W4247768107","https://openalex.org/W4252909492","https://openalex.org/W6684853765"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W3191490922","https://openalex.org/W2794038527","https://openalex.org/W1599154403","https://openalex.org/W2166828374"],"abstract_inverted_index":{"Checkpointing":[0],"is":[1],"the":[2,25,32,48,56,65,77,90,105,120,129],"most":[3],"widely":[4],"used":[5],"technique":[6],"in":[7,115],"high":[8,29],"performance":[9,30],"computing":[10,37],"systems":[11],"to":[12,47,64,76,103,123],"tolerate":[13],"fail-stop":[14],"errors":[15],"and":[16,36,61,71,74,86,118,132,137],"ensure":[17],"reliable":[18],"execution":[19],"of":[20,28,34,45,93,107,149],"parallel":[21,83,154],"applications.":[22],"However,":[23],"with":[24],"scaling":[26],"up":[27],"computers,":[31],"number":[33],"processors":[35],"nodes":[38,57],"increase":[39],"rapidly,":[40],"which":[41],"brings":[42],"I/O":[43,78,91,147],"impact":[44,92,148],"checkpointing":[46,108,150],"systems.":[49,155],"On":[50],"arriving":[51],"at":[52],"a":[53,98,124],"checkpoint,":[54],"all":[55],"generate":[58],"checkpoint":[59,112],"data":[60,75,113,121,133],"write":[62],"them":[63],"storage":[66],"system":[67,85],"simultaneously,":[68],"causing":[69],"burst":[70,130],"massive":[72],"traffics":[73],"infrastructure":[79],"including":[80],"interconnection":[81],"network,":[82],"file":[84],"storage.":[87],"To":[88],"mitigate":[89,146],"checkpointing,":[94],"this":[95,143],"paper":[96],"proposes":[97],"self-adaptive":[99,125],"random":[100,126],"delay":[101,127],"approach":[102,144],"control":[104],"writing":[106,119],"data.":[109],"By":[110],"generating":[111],"simultaneously":[114],"each":[116],"node":[117],"according":[122],"policy,":[128],"traffic":[131],"are":[134],"smoothed.":[135],"Experiment":[136],"theoretical":[138],"analysis":[139],"results":[140],"show":[141],"that":[142],"can":[145],"on":[151],"large":[152],"scale":[153]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}